Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint; the description adds the crucial behavioural fact that this tool only constructs transactions and never broadcasts, plus the conditional approve and the ordering requirement — exactly the context an agent needs to avoid treating it as an executor. It stops short of disclosing quote freshness/expiry, that slippage defaults to 3%, or what the returned objects look like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, and the most important facts — direction and the fact that the caller signs and sends — are front-loaded. Nothing is repeated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining what comes back, and it only gestures at 'them' requiring signature and ordering. For a four-parameter builder with a conditional step, an agent would benefit from knowing the return shape, whether an approve entry is always index 0, and how stale quotes are handled.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: amount (including the 'all' sentinel) and slippage_pct ('percent') are documented in the schema, while token and wallet carry only address patterns. The description adds real meaning by fixing the direction of the trade (token is what is sold, wallet is the seller) and by implying token must be an allowance-bearing ERC-20, but it does not explain slippage behaviour or 'all' resolution.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: builds a Montra sale transaction, with the exact direction stated (token -> HYPE) and the internal composition (conditional router approve, then the swap). The word 'sale' plus the direction cleanly separates it from build_buy_tx without the agent needing to open either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear workflow context: the output is unsigned, the caller must sign and send in order, and an approve appears only when needed. What is missing is naming the follow-up siblings (send_signed_tx, get_tx_status) and any exclusion, e.g. that this is not the tool to use if the wallet already holds an allowance or if the caller wants a buy.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.